CN115439452A - Capacitance product detection and evaluation system based on data analysis - Google Patents
Capacitance product detection and evaluation system based on data analysis Download PDFInfo
- Publication number
- CN115439452A CN115439452A CN202211107633.3A CN202211107633A CN115439452A CN 115439452 A CN115439452 A CN 115439452A CN 202211107633 A CN202211107633 A CN 202211107633A CN 115439452 A CN115439452 A CN 115439452A
- Authority
- CN
- China
- Prior art keywords
- capacitor
- defect
- pin
- image
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Fixed Capacitors And Capacitor Manufacturing Machines (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a capacitance product detection and evaluation system based on data analysis, belongs to the technical field of capacitance product detection, and comprises a first image acquisition module and the like. According to the invention, the packaging defect detection module can be used for conveniently detecting the packaging defect of the capacitor product, and the packaging defect result of the capacitor product can be accurately obtained; the structural defect detection module can conveniently detect the structural defects of the capacitor product and accurately judge whether the pins of the capacitor have defects of deletion and bending; through the defect analysis module, the quality of the capacitor produced in unit time according to the defect identification result of the packaging shell, the pin missing defect identification result and the pin bending defect identification result can be conveniently scored.
Description
Technical Field
The invention relates to the technical field of detection and evaluation of capacitor products, in particular to a data analysis-based capacitor product detection and evaluation system.
Background
In the factory detection and evaluation process of capacitor products, the traditional detection mode is mainly to identify and eliminate the packaging defects and the structural defects of the capacitor manually, then count the defects and evaluate the quality of the capacitor produced by each production line within a certain time. The mode is too dependent on manual work, the automation degree is low, the detection cost is high, and the detection efficiency is low. The above-mentioned problems need to be solved, and therefore, a system for detecting and evaluating a capacitive product based on data analysis is proposed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to solve the problem that the existing manual detection mode is too dependent on manual work, the degree of automation is low, the detection cost is high, and the detection efficiency is low, and a capacitance product detection and evaluation system based on data analysis is provided.
The invention solves the technical problem through the following technical scheme that the invention comprises a first image acquisition module, a packaging defect detection module, a second image acquisition module, a structure defect detection module, a defect analysis module and a storage module;
the first image acquisition module is used for acquiring an image containing a capacitor packaging shell, namely a packaging shell image;
the packaging defect detection module is used for preprocessing the packaging shell image, identifying the type of the capacitor and acquiring the defect identification result of the packaging shell of the capacitor;
the second image acquisition module is used for acquiring images of positions of two pins of the capacitor, namely pin images;
the structure defect detection module is used for preprocessing the pin image and acquiring a pin missing defect identification result and a pin bending defect identification result;
the defect analysis module is used for weighting and grading the quality of a capacitor product produced by the capacitor model in unit time according to a defect identification result of a packaging shell, a pin missing defect identification result and a pin bending defect identification result on the basis of the capacitor model;
the storage module is used for establishing a quality database corresponding to the capacitor model in unit time on the basis of the capacitor model, storing a packaging shell defect identification result, a pin missing defect identification result and pin bending defect identification result data of the capacitor produced in unit time corresponding to the capacitor model in the unit time in the quality database, and establishing an identification-model database.
Still further, the package housing image includes a side-shot image of the capacitor package housing and a top-shot/bottom-shot image of the capacitor package housing.
Furthermore, the packaging defect detection module comprises a first image preprocessing unit, an identification detection and identification unit and a first contour detection and identification unit; the first image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray scale processing on the packaged shell image; the identification detection and identification unit is used for identifying the capacitor package shape identification on the packaging shell through the trained first target identification network, acquiring a current capacitor package shape identification result, and acquiring a corresponding capacitor model according to the capacitor package shape identification result; the first contour detection and identification unit is used for carrying out contour detection processing on the image of the packaging shell, further judging whether the capacitor packaging shell has defects or not, and sending the current defect identification result of the capacitor packaging shell to the defect analysis module.
Further, the specific process of acquiring the capacitor model by the identifier detection and identification unit is as follows:
s11: uploading the identification result of the capacitor package shape identifier to an identifier-model database;
s12: and acquiring the capacitor model corresponding to the identification result of the capacitor package shape identification from the identification-model database.
Further, in the step S11, the identifier-model database stores a correspondence between the capacitor package shape identifier and the capacitor model.
Furthermore, the specific process of acquiring the defect identification result of the package shell by the first contour detection and identification unit is as follows:
s21: performing contour detection processing on the image of the packaging shell by using a contour detection function in OpenCv to obtain a capacitor side contour length value Lc and a top/bottom contour length value Ld;
s22: the capacitor side profile length value Lc and the top/bottom profile length value Ld obtained by detection in step S21 are corresponded to the capacitor side profile length value Lc in the defect-free state Standard of merit Top/bottom profile length value Ld Standard of merit Respectively carrying out difference processing to obtain a capacitor side contour length difference value Lc Difference (D) Difference Ld from top/bottom profile length Difference (D) ；
S23: the difference Lc between the side profile lengths of the capacitor Difference (D) Threshold value Lc of difference value with capacitor side contour length Threshold(s) Comparing and judging Lc Difference (D) Whether it is at Lc Threshold(s) In the range, the difference Ld of the top/bottom profile lengths of the capacitors is simultaneously measured Difference (D) Threshold Ld for difference with capacitor top/bottom profile length Threshold value Comparing and judging Ld Difference (D) Whether or not at Ld Threshold(s) Within the range, if any one is within the range of the difference threshold value, the capacitor packaging shell is indicated to have defects (packaging is poor and the surface is uneven), otherwise, the capacitor packaging shell is indicated to have no defects;
s24: and sending the current capacitor packaging shell defect identification result to a defect analysis module.
Furthermore, the structural defect detection module comprises a second image preprocessing unit, a pin identification unit and a second contour detection identification unit; the second image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray scale processing on the pin image; the pin identification unit is used for identifying pins in the pin image through a trained second target identification network, acquiring pin quantity information, judging whether the pins have missing defects or not, sending a pin missing defect identification result to the defect analysis module, cutting a target detection frame of the pin image from the image, pasting the target detection frame into a blank image to form a pin detection frame image, and sending the pin detection frame image to the second contour detection identification unit; the second contour detection and identification unit is used for carrying out contour detection processing on the pin detection frame image, further judging whether the capacitor pin has a bending defect or not, and sending a current capacitor pin bending defect identification result to the defect analysis module.
Furthermore, the specific process of the second contour detection and identification unit obtaining the pin bending defect identification result is as follows:
s31: carrying out contour detection processing on the image of the pin detection frame by using a contour detection function in OpenCv to obtain a contour length value Yci of each pin of the capacitor, wherein i is 1 or 2;
s32: comparing the profile length value Yci of each lead detected in step S31 with the profile length value Yc of the lead in the state without bending defects Standard of merit Performing difference processing to obtain the profile length difference value Yci of each pin Difference (D) ；
S33: the difference value Yci of the contour length of each pin Difference (D) Difference value threshold Yc with capacitor pin outline length Threshold(s) Comparing and judging Yci Difference (D) Whether or not it is in Yc Threshold(s) In the range, if the contour length difference of any pin is in the difference threshold range, the pin of the capacitor has a bending defect, otherwise, the pin of the capacitor does not have the bending defect;
s34: and sending the current pin bending defect identification result of the capacitor to a defect analysis module.
Compared with the prior art, the invention has the following advantages: the packaging defect detection module can be used for conveniently detecting the packaging defects of the capacitor product and accurately obtaining the packaging defect result of the capacitor product; the structural defect detection module can conveniently detect the structural defects of the capacitor product and accurately judge whether the pins of the capacitor have defects of deletion and bending; through the defect analysis module, the quality of the capacitor produced in unit time according to the defect identification result of the packaging shell, the pin missing defect identification result and the pin bending defect identification result can be conveniently scored.
Drawings
FIG. 1 is a block diagram of the architecture of the present invention.
Detailed Description
The following examples are given for the detailed implementation and the specific operation procedures, but the scope of the present invention is not limited to the following examples.
The embodiment provides a technical scheme: the utility model provides a capacitance product detects evaluation system based on data analysis, this system is applicable to the condenser that has regular shape, for example the encapsulation casing is cylinder or cuboid etc. this embodiment takes the encapsulation casing to describe as the condenser of cylinder, includes first image acquisition module, encapsulation defect detection module, second image acquisition module, structural defect detection module, defect analysis module, storage module.
In this embodiment, the first image obtaining module is configured to obtain an image of a package housing including a capacitor, that is, a package housing image, and transmit the image to the package defect detecting module, so that the package defect detecting module performs image processing and identification;
specifically, the first image acquisition module comprises two groups of high-definition cameras arranged on any side and above/below the capacitor, wherein the high-definition camera arranged on one side of the capacitor is used for acquiring a side-shot image containing a capacitor packaging shell, the high-definition camera arranged above/below the capacitor is used for acquiring a top-shot/bottom-shot image containing the capacitor packaging shell, so that defects on the capacitor packaging shell can be identified conveniently in the following process, and the packaging shell image comprises a side-shot image and a top-shot/bottom-shot image;
as a better preference, two sets of high definition cameras are installed at the designated positions on the production line tail end conveying platform, the optical axis of the high definition camera arranged on one side of the capacitor is perpendicular to the axis of the capacitor packaging shell, and the optical axis of the high definition camera arranged above/below the capacitor is located on the axis of the capacitor packaging shell, so that images at designated visual angles can be conveniently acquired, and meanwhile, the maintenance is also convenient.
In this embodiment, the package defect detecting module includes a first image preprocessing unit, an identifier detecting and identifying unit, and a first contour detecting and identifying unit; the first image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray processing on the packaging shell image, and respectively sending the preprocessed packaging shell image to the identification detection and recognition unit and the first contour detection and recognition unit, so that the image quality is effectively improved through image preprocessing, and the identification detection and recognition and the contour detection and recognition work are facilitated; the identification detection and identification unit is used for identifying the capacitor package shape identification on the packaging shell through the trained first target identification network, acquiring a current capacitor package shape identification result, acquiring a corresponding capacitor model according to the capacitor package shape identification result, and sending capacitor model information to the defect analysis module; the first contour detection and identification unit is used for carrying out contour detection processing on an image of the packaging shell, acquiring a current capacitor side contour length value and a top/bottom contour length value, carrying out difference comparison on the current capacitor side contour length value and the top/bottom contour length value in a defect-free state, comparing a difference result with a difference threshold value, judging that the capacitor packaging shell is defect-free if the difference result is within the range of the difference threshold value, judging that the capacitor packaging shell is defective if the difference result is not within the range of the difference threshold value, and sending a defect identification result of the current capacitor packaging shell to the defect analysis module;
specifically, the specific process of obtaining the corresponding capacitor model according to the capacitor package shape identification result is as follows:
s11: uploading the identification result of the capacitor package shape identifier to an identifier-model database;
s12: and acquiring the capacitor model corresponding to the identification result of the capacitor package shape identification from the identification-model database.
In the step S11, the identifier-model database stores a corresponding relationship between the capacitor package shape identifier and the capacitor model, and supports the corresponding relationship between the capacitor package shape identifier and the capacitor model according to different capacitor products, so that the identifier-model database has good extensibility.
Preferably, the capacitor package shape identifier may be customized as needed, and then the first target recognition network is trained by using a package shape identifier sample picture containing the definition.
Specifically, the processing procedure of the first contour detection and identification unit is as follows:
s21: carrying out contour detection processing on the image of the packaging shell by using a contour detection function in OpenCv to obtain a capacitor side contour length value Lc and a top/bottom contour length value Ld;
s22: the capacitor side profile length value Lc and the top/bottom profile length value Ld obtained in the step S21 are corresponded to the capacitor side profile length value Lc in the defect-free state Standard of merit Top/bottom profile length value Ld Standard of reference Respectively carrying out difference processing to obtain a capacitor side contour length difference value Lc Difference (D) Difference Ld from top/bottom profile length Difference (D) ；
S23: the difference Lc between the side profile lengths of the capacitors Difference (D) Threshold value Lc of difference value with capacitor side contour length Threshold(s) Comparing and judging Lc Difference (D) Whether it is at Lc Threshold value In the range, the top/bottom profile length difference Ld of the capacitor is simultaneously measured Difference between Threshold Ld for difference with capacitor top/bottom profile length Threshold(s) Comparing and judging Ld Difference (D) Whether or not at Ld Threshold value Within the range, if any one is within the range of the difference threshold value, the capacitor packaging shell is indicated to have defects (packaging is poor and the surface is uneven), otherwise, the capacitor packaging shell is indicated to have no defects;
s24: and sending the current capacitor packaging shell defect identification result to a defect analysis module.
In this embodiment, the second image obtaining module is configured to obtain images of positions of two pins of the capacitor, that is, pin images, and transmit the images to the structural defect detecting module, so that the structural defect detecting module performs image processing and identification;
specifically, the second image acquisition module is a group of high-definition cameras arranged on any side of the capacitor and used for acquiring side-shot images of positions of two pins of the capacitor.
Preferably, the group of high-definition cameras arranged on any side of the capacitor is used for acquiring side-shot images of pins of the capacitor, optical axes of the group of high-definition cameras arranged on any side of the capacitor are perpendicular to a connecting line of starting ends of two pins of the capacitor, and similarly, the group of high-definition cameras are arranged at a specified position on a tail end conveying platform of a production line.
In this embodiment, the structural defect detecting module includes a second image preprocessing unit, a pin identifying unit, and a second contour detection identifying unit; the second image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray level processing on the pin image, sending the preprocessed packaging shell image to the pin identification unit, and effectively improving the image quality through image preprocessing so as to facilitate the pin identification and contour detection identification work; the pin identification unit is used for identifying pins in the pin image through a trained second target identification network, acquiring pin quantity information, judging whether the pins have missing defects or not, sending a pin missing defect identification result to the defect analysis module, cutting a target detection frame of the pin image from the image, pasting the target detection frame into a blank image to form a pin detection frame image, and sending the pin detection frame image to the second contour detection identification unit; the second contour detection and identification unit is used for carrying out contour detection processing on the pin detection frame image, obtaining contour length values of all pins of the current capacitor, respectively carrying out difference comparison on the contour length values of all the pins of the current capacitor and the contour length values of the pins in a non-bending defect state, comparing the difference results with difference threshold values, judging that the pins of the capacitor have no bending defects if the contour length values of all the pins of the current capacitor are within the range of the difference threshold values, judging that the pins of the capacitor have the bending defects if the contour length values of all the pins of the current capacitor are not within the range of the difference values, and sending the bending defect identification results of the pins of the current capacitor to the defect analysis module.
Specifically, in the process of judging whether the pins have the missing defects according to the pin number information, when the number of the target detection frames is two, the pins are judged to have no missing defects, and when the number of the target detection frames is one or zero, the pins are judged to have the missing defects.
It should be noted that when the number of the target detection frames is zero, the subsequent contour detection and identification process is entered.
Specifically, the processing procedure of the second contour detection and identification unit is as follows:
s31: carrying out contour detection processing on the image of the pin detection frame by using a contour detection function in OpenCv to obtain a contour length value Yci of each pin of the capacitor, wherein i is 1 or 2;
s32: comparing the profile length value Yci of each lead detected in step S31 with the profile length value Yc of the lead in the state without bending defects Standard of merit Performing difference processing to obtain the profile length difference value Yci of each pin Difference between ；
S33: the difference value Yci of the contour length of each pin Difference (D) Difference value Yc with the contour length of the capacitor pin Threshold(s) Comparing and judging Yci Difference (D) Whether or not it is in Yc Threshold(s) In the range, if the contour length difference of any pin is in the difference threshold range, the pin of the capacitor has a bending defect, otherwise, the pin of the capacitor does not have the bending defect;
s34: sending the current capacitor pin bending defect identification result to a defect analysis module;
in this embodiment, the defect analysis module is configured to perform, based on the capacitor model, a weighted scoring on the quality of a capacitor product produced by the capacitor model in a unit time according to the package housing defect identification result, the pin missing defect identification result, and the pin bending defect identification result.
Specifically, the weights of the factors (the package defect identification result, the pin missing defect identification result, and the pin bending defect identification result) in the scoring can be flexibly set according to the difference of the capacitor products.
Preferably, the capacitor quality scoring formula in this embodiment is as follows:
f is the number of capacitors with packaging shell defects in the capacitor of the model in unit time, Q is the number of capacitors with pin missing defects in the capacitor of the model in unit time, Z is the number of capacitors with pin bending defects in the capacitor of the model in unit time, w1, w2 and w3 are corresponding weight ratios, and the sum of w1, w2 and w3 is 1.
In this embodiment, the storage module is configured to establish a quality database corresponding to the capacitor model in a unit time based on the capacitor model, wherein the quality database stores a package casing defect identification result, a pin missing defect identification result, and pin bending defect identification result data of the capacitor produced in the unit time corresponding to the capacitor model, and is used to establish an identifier-model database.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (7)
1. A capacitance product detection and evaluation system based on data analysis is characterized by comprising a first image acquisition module, a packaging defect detection module, a second image acquisition module, a structure defect detection module, a defect analysis module and a storage module;
the first image acquisition module is used for acquiring an image of a capacitor-containing packaging shell, namely a packaging shell image;
the packaging defect detection module is used for preprocessing the packaging shell image, identifying the type of the capacitor and acquiring the defect identification result of the packaging shell of the capacitor;
the second image acquisition module is used for acquiring images of positions of two pins of the capacitor, namely pin images;
the structure defect detection module is used for preprocessing the pin image and acquiring a pin missing defect identification result and a pin bending defect identification result;
the defect analysis module is used for weighting and scoring the quality of a capacitor product produced by the capacitor model in unit time according to a defect identification result of the packaging shell, a pin missing defect identification result and a pin bending defect identification result on the basis of the capacitor model;
the storage module is used for establishing a quality database corresponding to the capacitor model in unit time on the basis of the capacitor model, storing a packaging shell defect identification result, a pin missing defect identification result and pin bending defect identification result data of the capacitor produced in unit time corresponding to the capacitor model in the unit time in the quality database, and establishing an identification-model database.
2. The capacitive product detection and evaluation system based on data analysis of claim 1, wherein: the package housing image includes a side-shot image of the capacitor package housing and a top-shot/bottom-shot image of the capacitor package housing.
3. The capacitive product detection and evaluation system based on data analysis of claim 1, wherein: the packaging defect detection module comprises a first image preprocessing unit, an identification detection and identification unit and a first contour detection and identification unit; the first image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray scale processing on the image of the packaging shell; the identification detection and identification unit is used for identifying the capacitor package shape identification on the packaging shell through the trained first target identification network, acquiring a current capacitor package shape identification result, and acquiring a corresponding capacitor model according to the capacitor package shape identification result; the first contour detection and identification unit is used for carrying out contour detection processing on the image of the packaging shell, further judging whether the capacitor packaging shell has defects or not, and sending the current defect identification result of the capacitor packaging shell to the defect analysis module.
4. The system of claim 3, wherein the capacitive product inspection and evaluation system comprises: the specific process of acquiring the model of the capacitor by the identification detection and identification unit is as follows:
s11: uploading the identification result of the capacitor package shape identifier to an identifier-model database;
s12: and acquiring the capacitor model corresponding to the identification result of the capacitor package shape identification from the identification-model database.
5. The system of claim 4, wherein the capacitive product inspection and evaluation system comprises: the specific process of acquiring the defect identification result of the packaging shell by the first contour detection and identification unit is as follows:
s21: performing contour detection processing on the image of the packaging shell by using a contour detection function in OpenCv to obtain a capacitor side contour length value Lc and a top/bottom contour length value Ld;
s22: the capacitor side profile length value Lc and the top/bottom profile length value Ld obtained in the step S21 are corresponded to the capacitor side profile length value Lc in the defect-free state Standard of merit Top/bottom profile length values Ld Standard of reference Respectively carrying out difference processing to obtain a capacitor side contour length difference value Lc Difference (D) Difference Ld from the top/bottom profile length Difference (D) ；
S23: the difference Lc between the side profile lengths of the capacitor Difference between And capacitor side profile length difference threshold Lc Threshold value Comparing and judging Lc Difference (D) Whether it is at Lc Threshold(s) In the range, the top/bottom profile length difference Ld of the capacitor is simultaneously measured Difference (D) And capacitor top/bottom profile length difference threshold Ld Threshold value Comparing and judging Ld Difference (D) Whether or not at Ld Threshold(s) Within the range, if any one is within the range of the difference threshold value, the capacitor packaging shell is indicated to have defects (packaging is poor and the surface is uneven), otherwise, the capacitor packaging shell is indicated to have no defects;
s24: and sending the current defect identification result of the capacitor packaging shell to a defect analysis module.
6. The system of claim 5, wherein the system comprises: the structural defect detection module comprises a second image preprocessing unit, a pin identification unit and a second contour detection identification unit; the second image preprocessing unit is used for sequentially carrying out noise reduction, image enhancement and gray scale processing on the pin image; the pin identification unit is used for identifying pins in the pin image through a trained second target identification network, acquiring pin quantity information, judging whether the pins have missing defects or not, sending a pin missing defect identification result to the defect analysis module, cutting a target detection frame of the pin image from the image, pasting the target detection frame into a blank image to form a pin detection frame image, and sending the pin detection frame image to the second contour detection identification unit; the second contour detection and identification unit is used for carrying out contour detection processing on the pin detection frame image so as to judge whether the capacitor pin has a bending defect or not and sending a current capacitor pin bending defect identification result to the defect analysis module;
s24: and sending the current defect identification result of the capacitor packaging shell to a defect analysis module.
7. The system of claim 6, wherein the capacitive product inspection and evaluation system comprises: the specific process of the second contour detection and identification unit for obtaining the pin bending defect identification result is as follows:
s31: carrying out contour detection processing on the image of the pin detection frame by using a contour detection function in OpenCv to obtain a contour length value Yci of each pin of the capacitor, wherein i is 1 or 2;
s32: comparing the profile length value Yci of each lead detected in step S31 with the profile length value Yc of the lead in the state without bending defects Standard of reference Performing difference processing to obtain the profile length difference value Yci of each pin Difference (D) ；
S33: the difference value Yci of the contour length of each pin Difference (D) Difference value threshold Yc with capacitor pin outline length Threshold value Comparing and judging Yci Difference (D) Whether or not it is in Yc Threshold(s) In the range, if the contour length difference of any pin is in the difference threshold range, the pin of the capacitor has a bending defect, otherwise, the pin of the capacitor does not have the bending defect;
s34: and sending the current pin bending defect identification result of the capacitor to a defect analysis module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211107633.3A CN115439452B (en) | 2022-09-13 | 2022-09-13 | Capacitance product detection and evaluation system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211107633.3A CN115439452B (en) | 2022-09-13 | 2022-09-13 | Capacitance product detection and evaluation system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115439452A true CN115439452A (en) | 2022-12-06 |
| CN115439452B CN115439452B (en) | 2023-04-11 |
Family
ID=84246571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211107633.3A Active CN115439452B (en) | 2022-09-13 | 2022-09-13 | Capacitance product detection and evaluation system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115439452B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116310424A (en) * | 2023-05-17 | 2023-06-23 | 青岛创新奇智科技集团股份有限公司 | Equipment quality assessment method, device, terminal and medium based on image recognition |
| CN116678827A (en) * | 2023-05-31 | 2023-09-01 | 天芯电子科技(江阴)有限公司 | LGA (land grid array) packaging pin detection system of high-current power supply module |
| CN117038494A (en) * | 2023-10-10 | 2023-11-10 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060194353A1 (en) * | 2005-02-28 | 2006-08-31 | Ridgetop Group, Inc. | Method and circuit for the detection of solder-joint failures in a digital electronic package |
| US7420791B1 (en) * | 2004-08-09 | 2008-09-02 | Intersil Americas Inc. | Fault signature system for power management integrated circuits |
| US20110156717A1 (en) * | 2009-12-31 | 2011-06-30 | Su-Wei Tsai | Electrical connection defect detection system and method |
| CN103808732A (en) * | 2014-01-21 | 2014-05-21 | 图灵视控（北京）科技有限公司 | Capacitance detection system and capacitance detection method based on machine vision |
| CN105044114A (en) * | 2015-04-27 | 2015-11-11 | 中国人民解放军理工大学 | Electrolytic capacitor appearance package defect image detection system and electrolytic capacitor appearance package defect image detection method |
| CN105044115A (en) * | 2015-06-29 | 2015-11-11 | 南通蒂龙针织制衣有限公司 | Novel electrolytic capacitor pin defect detection device |
| CN204789357U (en) * | 2015-04-27 | 2015-11-18 | 中国人民解放军理工大学 | Electrolytic capacitor outward appearance packing defect image detection system |
| CN109785316A (en) * | 2019-01-22 | 2019-05-21 | 湖南大学 | A kind of apparent defect inspection method of chip |
| CN109967365A (en) * | 2018-12-27 | 2019-07-05 | 江苏理工学院 | A kind of stud capacitor appearance detection system and its method based on machine vision |
| US20190304350A1 (en) * | 2018-03-29 | 2019-10-03 | Solomon Systech (Shenzhen) Limited | Panel Defect Detection Method and a Display Driver Apparatus Incorporating the Same |
| CN110992336A (en) * | 2019-12-02 | 2020-04-10 | 东莞西尼自动化科技有限公司 | Small sample defect detection method based on image processing and artificial intelligence |
| CN112348840A (en) * | 2020-10-19 | 2021-02-09 | 江苏师范大学 | QFP chip pin defect discrimination method based on pixel region growth |
| CN113070228A (en) * | 2021-03-12 | 2021-07-06 | 厦门泓天自动化科技有限公司 | Full-automatic capacitance monitoring machine |
| CN114445330A (en) * | 2021-12-17 | 2022-05-06 | 航天科工防御技术研究试验中心 | Method and system for detecting appearance defects of components |
-
2022
- 2022-09-13 CN CN202211107633.3A patent/CN115439452B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7420791B1 (en) * | 2004-08-09 | 2008-09-02 | Intersil Americas Inc. | Fault signature system for power management integrated circuits |
| US20060194353A1 (en) * | 2005-02-28 | 2006-08-31 | Ridgetop Group, Inc. | Method and circuit for the detection of solder-joint failures in a digital electronic package |
| US20110156717A1 (en) * | 2009-12-31 | 2011-06-30 | Su-Wei Tsai | Electrical connection defect detection system and method |
| CN103808732A (en) * | 2014-01-21 | 2014-05-21 | 图灵视控（北京）科技有限公司 | Capacitance detection system and capacitance detection method based on machine vision |
| CN204789357U (en) * | 2015-04-27 | 2015-11-18 | 中国人民解放军理工大学 | Electrolytic capacitor outward appearance packing defect image detection system |
| CN105044114A (en) * | 2015-04-27 | 2015-11-11 | 中国人民解放军理工大学 | Electrolytic capacitor appearance package defect image detection system and electrolytic capacitor appearance package defect image detection method |
| CN105044115A (en) * | 2015-06-29 | 2015-11-11 | 南通蒂龙针织制衣有限公司 | Novel electrolytic capacitor pin defect detection device |
| US20190304350A1 (en) * | 2018-03-29 | 2019-10-03 | Solomon Systech (Shenzhen) Limited | Panel Defect Detection Method and a Display Driver Apparatus Incorporating the Same |
| CN109967365A (en) * | 2018-12-27 | 2019-07-05 | 江苏理工学院 | A kind of stud capacitor appearance detection system and its method based on machine vision |
| CN109785316A (en) * | 2019-01-22 | 2019-05-21 | 湖南大学 | A kind of apparent defect inspection method of chip |
| CN110992336A (en) * | 2019-12-02 | 2020-04-10 | 东莞西尼自动化科技有限公司 | Small sample defect detection method based on image processing and artificial intelligence |
| CN112348840A (en) * | 2020-10-19 | 2021-02-09 | 江苏师范大学 | QFP chip pin defect discrimination method based on pixel region growth |
| CN113070228A (en) * | 2021-03-12 | 2021-07-06 | 厦门泓天自动化科技有限公司 | Full-automatic capacitance monitoring machine |
| CN114445330A (en) * | 2021-12-17 | 2022-05-06 | 航天科工防御技术研究试验中心 | Method and system for detecting appearance defects of components |
Non-Patent Citations (3)
| Title |
|---|
| CHENG CHENG 等: "Capacitance pin defect detection based on deep learning" * |
| 苏朝阳: "基于图像处理的电容器外观缺陷检测系统研究与开发" * |
| 陈佐政: "基于机器视觉的电容器外观缺陷检测系统研发" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116310424A (en) * | 2023-05-17 | 2023-06-23 | 青岛创新奇智科技集团股份有限公司 | Equipment quality assessment method, device, terminal and medium based on image recognition |
| CN116310424B (en) * | 2023-05-17 | 2023-08-18 | 青岛创新奇智科技集团股份有限公司 | Equipment quality assessment method, device, terminal and medium based on image recognition |
| CN116678827A (en) * | 2023-05-31 | 2023-09-01 | 天芯电子科技(江阴)有限公司 | LGA (land grid array) packaging pin detection system of high-current power supply module |
| CN117038494A (en) * | 2023-10-10 | 2023-11-10 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
| CN117038494B (en) * | 2023-10-10 | 2023-12-15 | 天津芯成半导体有限公司 | Auxiliary intelligent detection system for chip processing industry |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115439452B (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115439452B (en) | Capacitance product detection and evaluation system based on data analysis | |
| CN106226325B (en) | A kind of seat surface defect detecting system and its method based on machine vision | |
| CN111402226A (en) | Surface defect detection method based on cascade convolution neural network | |
| CN201218723Y (en) | Optoelectronic non-contact type image detection apparatus | |
| CN105335692A (en) | Tire X-ray image detection and identification method and system | |
| CN106383121B (en) | It is a kind of can adaptive multi-brand visible detection method and system | |
| CN116109635B (en) | Method, device, equipment and medium for detecting surface quality of composite suspension insulator | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| CN111504381A (en) | Terminal row product online detection device and detection method thereof | |
| CN113792725B (en) | Component detection device and method | |
| CN114596301A (en) | Coating roller surface defect detection system adopting 3D line laser profile technology | |
| CN112415013A (en) | Copper foil defect detection system | |
| CN103718024A (en) | Plate glass inspection device, plate glass inspection method, plate glass manufacturing device, and plate glass manufacturing method | |
| CN115266743A (en) | System and method for evaluating chip quality under nondestructive testing | |
| CN110763688B (en) | System and method for detecting redundant materials in blind holes | |
| CN113780488A (en) | Scratching and scratching defect detection method based on position polymerization degree | |
| CN111015208A (en) | Automatic assembly detection device and method for charging equipment | |
| CN117350967B (en) | Optical detection-based wafer appearance defect detection system and method | |
| CN111474181A (en) | Panel defect detecting and classifying system in box forming process stage | |
| CN210773933U (en) | Product appearance on-line measuring device | |
| CN111649681B (en) | Corrugated paper thickness detection method and corrugated paper production quality monitoring system | |
| CN211678855U (en) | Electronic component product appearance on-line measuring device | |
| CN117876376B (en) | High-speed multifunctional connector quality visual detection method | |
| CN116907360B (en) | RO (reverse osmosis) membrane gel line width detection system and detection method based on machine vision | |
| CN116843615B (en) | Lead frame intelligent total inspection method based on flexible light path |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |